{"id":"https://openalex.org/W4399418624","doi":"https://doi.org/10.1145/3652583.3658419","title":"Fine-Tuning Large Language Models for Private Document Retrieval: A Tutorial","display_name":"Fine-Tuning Large Language Models for Private Document Retrieval: A Tutorial","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418624","doi":"https://doi.org/10.1145/3652583.3658419"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658419","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658419","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658419","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658419","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009937487","display_name":"Frank Sommers","orcid":"https://orcid.org/0009-0006-0790-5015"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Frank Sommers","raw_affiliation_strings":["Docusure, Inc., Orange, CA, USA"],"raw_orcid":"https://orcid.org/0009-0006-0790-5015","affiliations":[{"raw_affiliation_string":"Docusure, Inc., Orange, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010183423","display_name":"Alisa Kongthon","orcid":"https://orcid.org/0009-0009-8682-5006"},"institutions":[{"id":"https://openalex.org/I60837268","display_name":"King Mongkut's University of Technology Thonburi","ror":"https://ror.org/0057ax056","country_code":"TH","type":"education","lineage":["https://openalex.org/I60837268"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Alisa Kongthon","raw_affiliation_strings":["King Mongkuts University of Technology Thonburi, Bangkok, Thailand"],"raw_orcid":"https://orcid.org/0009-0009-8682-5006","affiliations":[{"raw_affiliation_string":"King Mongkuts University of Technology Thonburi, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031930609","display_name":"Sarawoot Kongyoung","orcid":"https://orcid.org/0009-0001-3375-8809"},"institutions":[{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Sarawoot Kongyoung","raw_affiliation_strings":["National Electronics and Computer Technology Center, Pathumthani, Thailand"],"raw_orcid":"https://orcid.org/0009-0001-3375-8809","affiliations":[{"raw_affiliation_string":"National Electronics and Computer Technology Center, Pathumthani, Thailand","institution_ids":["https://openalex.org/I14316845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009937487"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6623,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73205111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1319","last_page":"1320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9348999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.695549726486206},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5997228026390076},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.593755841255188},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.41271692514419556},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39480873942375183},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32141008973121643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695549726486206},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5997228026390076},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.593755841255188},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.41271692514419556},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39480873942375183},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32141008973121643},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658419","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658419","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658419","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658419","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658419","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658419","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418624.pdf","grobid_xml":"https://content.openalex.org/works/W4399418624.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4213212078","https://openalex.org/W391760326","https://openalex.org/W2254930926","https://openalex.org/W2358863338","https://openalex.org/W2187227032","https://openalex.org/W2112788825","https://openalex.org/W2284631983","https://openalex.org/W1963735073","https://openalex.org/W2027019938"],"abstract_inverted_index":{"Large":[0],"Multi-Modal":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"are":[5],"trained":[6],"on":[7,103],"vast":[8],"amounts":[9],"of":[10,16,67],"publicly":[11,43],"available":[12],"data.":[13,110],"Yet,":[14],"most":[15],"the":[17,52,65],"world's":[18],"data":[19,38,63,79],"is":[20],"not":[21],"public:":[22],"Health":[23],"care":[24],"records,":[25,29],"financial":[26],"documents,":[27],"court":[28],"or":[30],"government":[31],"civil":[32],"registry":[33],"records":[34],"contain":[35],"sensitive,":[36,61,108],"personal":[37],"that":[39],"cannot":[40],"be":[41],"shared":[42],"as":[44],"training":[45],"input":[46],"for":[47,95],"LLMs.":[48],"This":[49],"tutorial":[50],"reviews":[51],"latest":[53],"research":[54],"and":[55,86,100],"practical":[56],"experiences":[57],"in":[58,64,91],"working":[59],"with":[60,77],"private":[62,78,109],"context":[66],"LLM-assisted":[68],"multimedia":[69,104],"document":[70,96,105],"retrieval.":[71],"Key":[72],"topics":[73],"include":[74],"fine-tuning":[75],"LLMs":[76,90],"using":[80],"Differential":[81],"Privacy,":[82],"federated":[83],"learning":[84],"techniques,":[85],"deploying":[87],"privately":[88],"fine-tuned":[89],"a":[92],"secure":[93],"manner":[94],"classification,":[97],"named":[98],"entity-recognition,":[99],"question":[101],"answering":[102],"repositories":[106],"containing":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}